{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:06:52Z","timestamp":1772906812166,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation of China","award":["62206194"],"award-info":[{"award-number":["62206194"]}]},{"name":"Natural Science Foundation of Jiangsu Province","award":["BK20220488"],"award-info":[{"award-number":["BK20220488"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635847","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"769-778","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Better Chinese Spelling Check for Search Engines: A New Dataset and Strong Baseline"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7050-9811","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"first","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4381-1599","authenticated-orcid":false,"given":"Zilong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0075-8282","authenticated-orcid":false,"given":"Zecheng","family":"Tang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6286-7529","authenticated-orcid":false,"given":"Juntao","family":"Li","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5119-5196","authenticated-orcid":false,"given":"Zhihui","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0961-1479","authenticated-orcid":false,"given":"Kunlong","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1712-4263","authenticated-orcid":false,"given":"Jinxiong","family":"Chang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9964-6298","authenticated-orcid":false,"given":"Qishen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9478-8107","authenticated-orcid":false,"given":"Zhongyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.184"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of Natural Language Processing Pacific Rim Symposium","volume":"95","author":"Chang Chao-Huang","year":"1995","unstructured":"Chao-Huang Chang. 1995. A new approach for automatic Chinese spelling correction. In Proceedings of Natural Language Processing Pacific Rim Symposium, Vol. 95. Citeseer, 278--283."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.gebnlp-1.14"},{"key":"e_1_3_2_1_4_1","volume-title":"Learning towards Selective Data Augmentation for Dialogue Generation. arXiv preprint arXiv:2303.09719","author":"Chen Xiuying","year":"2023","unstructured":"Xiuying Chen, Mingzhe Li, Jiayi Zhang, Xiaoqiang Xia, Chen Wei, Jianwei Cui, Xin Gao, Xiangliang Zhang, and Rui Yan. 2023. Learning towards Selective Data Augmentation for Dialogue Generation. arXiv preprint arXiv:2303.09719 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.81"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_7_1","volume-title":"Reaching human-level performance in automatic grammatical error correction: An empirical study. arXiv preprint arXiv:1807.01270","author":"Ge Tao","year":"2018","unstructured":"Tao Ge, Furu Wei, and Ming Zhou. 2018. Reaching human-level performance in automatic grammatical error correction: An empirical study. arXiv preprint arXiv:1807.01270 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.122"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5522"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.464"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.287"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557636"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1119"},{"key":"e_1_3_2_1_14_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations.","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.56"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.252"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.237"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.233"},{"key":"e_1_3_2_1_20_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30228-5_33"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(91)90066-U"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.bea-1.16"},{"key":"e_1_3_2_1_24_1","volume-title":"https:\/\/openai.com\/blog\/chatgpt","author":"Introducing AI.","year":"2023","unstructured":"OpenAI. 2023. Introducing ChatGPT. (2023). https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_1_25_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_26_1","volume-title":"Francc ois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Francc ois Yvon, Matthias Gall\u00e9, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3106"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.216"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1273"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_31_1","unstructured":"Shaohua Wu Xudong Zhao Tong Yu Rongguo Zhang Chong Shen Hongli Liu Feng Li Hong Zhu Jiangang Luo Liang Xu et al. 2021. Yuan 1.0: Large-scale pre-trained language model in zero-shot and few-shot learning. arXiv preprint arXiv:2110.04725 (2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Seventh SIGHAN Workshop on Chinese Language Processing. 35--42","author":"Wu Shih-Hung","year":"2013","unstructured":"Shih-Hung Wu, Chao-Lin Liu, and Lung-Hao Lee. 2013. Chinese spelling check evaluation at SIGHAN bake-off 2013. In Proceedings of the Seventh SIGHAN Workshop on Chinese Language Processing. 35--42."},{"key":"e_1_3_2_1_33_1","unstructured":"xiaobo liang Lijun Wu Juntao Li Yue Wang Qi Meng Tao Qin Wei Chen Min Zhang and Tie-Yan Liu. 2021. R-Drop: Regularized Dropout for Neural Networks. In Advances in Neural Information Processing Systems A. Beygelzimer Y. Dauphin P. Liang and J. Wortman Vaughan (Eds.). https:\/\/openreview.net\/forum?id=bw5Arp3O3eY"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3120"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.64"},{"key":"e_1_3_2_1_36_1","volume-title":"Overview of SIGHAN 2014 bake-off for Chinese spelling check. In Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing. 126--132","author":"Yu Liang-Chih","year":"2014","unstructured":"Liang-Chih Yu, Lung-Hao Lee, Yuen-Hsien Tseng, and Hsin-Hsi Chen. 2014. Overview of SIGHAN 2014 bake-off for Chinese spelling check. In Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing. 126--132."},{"key":"e_1_3_2_1_37_1","volume-title":"Baochang Ma Qiang Niu, and Xiangang Li.","author":"Yunjie Ji Yong Deng","year":"2023","unstructured":"Yong Deng Yunjie Ji, Yiping Peng Yan Gong, Baochang Ma Qiang Niu, and Xiangang Li. 2023. BELLE: Be Everyone's Large Language model Engine. https:\/\/github.com\/LianjiaTech\/BELLE."},{"key":"e_1_3_2_1_38_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075250"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.198"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.82"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557416"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.98"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","location":"Merida Mexico","acronym":"WSDM '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635847","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:47:49Z","timestamp":1755823669000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":43,"alternative-id":["10.1145\/3616855.3635847","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635847","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}